One in six adults in the United States has low literacy skills and face difficulties with daily literacy tasks. These concerns prompted the Institute of Education Sciences to fund the Center for the Study of Adult Literacy, a research center that focuses on adult literacy for adults who read between grades 3 to 8. This presentation describes how conversation-based computer agents can help them improve their comprehension skills by holding conversations in natural language. The AutoTutor system on the web implements three-party conversations, called trialogues, where two agents (such as a tutor and a peer) interact with the adult. AutoTutor trains comprehension strategies in 35 lessons that target the theoretical levels of words, the meaning of the explicit text, the situation model with inferences, rhetorical structures, and digital technologies. Data mining procedures have been pursued in detecting different clusters of readers and the adults’ engagement (versus disengagement) in the AutoTutor interaction, based on the accuracy and response times to questions that the conversational agents ask the adults. Improvements in comprehension were found on three different psychometric tests for three out of four clusters of readers.